Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    signs of equality in programming code or mathematical expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    programming libraries and utilities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nonUne
    -0.49
    pektive
    -0.45
     halben
    -0.43
     desafío
    -0.43
     identity
    -0.40
     Provinz
    -0.40
    ￡
    -0.39
     inscri
    -0.38
     comesti
    -0.38
    UserScript
    -0.38
    POSITIVE LOGITS
    MemoryWarning
    0.78
    fjspx
    0.74
     AssemblyCulture
    0.68
     LoggerFactory
    0.68
    tagHelperRunner
    0.67
    ArgumentParser
    0.61
    basicConfig
    0.57
    LookAnd
    0.55
    帖最后由
    0.54
    addContainerGap
    0.53
    Act Density 0.010%

    No Known Activations